{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KOV4OJOT4CA2YKBWAOMVA5JDWS","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"01180db3fef93043d2331d7b2f089cecea30477fdb474cf0be2fb9dbf1910e48","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-09T08:54:20Z","title_canon_sha256":"8dee88ee96f6bdd0da98c961cc3b0372c34253c26ddf65426faadde117886775"},"schema_version":"1.0","source":{"id":"2512.08371","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.08371","created_at":"2026-05-27T01:04:53Z"},{"alias_kind":"arxiv_version","alias_value":"2512.08371v4","created_at":"2026-05-27T01:04:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.08371","created_at":"2026-05-27T01:04:53Z"},{"alias_kind":"pith_short_12","alias_value":"KOV4OJOT4CA2","created_at":"2026-05-27T01:04:53Z"},{"alias_kind":"pith_short_16","alias_value":"KOV4OJOT4CA2YKBW","created_at":"2026-05-27T01:04:53Z"},{"alias_kind":"pith_short_8","alias_value":"KOV4OJOT","created_at":"2026-05-27T01:04:53Z"}],"graph_snapshots":[{"event_id":"sha256:99738a8625895914a382042a34992605f2022c71bd02abc6b2cfe74719eddfdf","target":"graph","created_at":"2026-05-27T01:04:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2512.08371/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Datasets may contain observations with multiple labels. If the labels are not mutually exclusive, and if the labels vary greatly in frequency, obtaining a sample that includes sufficient observations with scarcer labels to make inferences about those labels, and which deviates from the population frequencies in a known manner, creates challenges. In this paper, we consider a multivariate Bernoulli distribution as our underlying distribution of a multi-label problem. We present a novel sampling algorithm that takes label dependencies into account. It uses observed label frequencies to estimate ","authors_text":"Andrew W. Brown, Colby J. Vorland, Donna L. Maney, Simon Chung","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-09T08:54:20Z","title":"A Multivariate Bernoulli-Based Sampling Method for Multi-Label Data with Application to Meta-Research"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.08371","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:05aba426833f7a1e23a29cf1a1ce1ed4b4c60f364f4fb79e768dbdec05fff2d9","target":"record","created_at":"2026-05-27T01:04:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"01180db3fef93043d2331d7b2f089cecea30477fdb474cf0be2fb9dbf1910e48","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-09T08:54:20Z","title_canon_sha256":"8dee88ee96f6bdd0da98c961cc3b0372c34253c26ddf65426faadde117886775"},"schema_version":"1.0","source":{"id":"2512.08371","kind":"arxiv","version":4}},"canonical_sha256":"53abc725d3e081ac28360399507523b4b44212cdec62ff9d808d4125fe2257ec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53abc725d3e081ac28360399507523b4b44212cdec62ff9d808d4125fe2257ec","first_computed_at":"2026-05-27T01:04:53.528534Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:04:53.528534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BCeDp/B5hz59Rhj789kuum7l1wjt8Hf8AcRR1PMAHagHRDyVJIAEXGBvYAM7MgriNt5Zg/2Ds5YgXV1r2+nCAg==","signature_status":"signed_v1","signed_at":"2026-05-27T01:04:53.529252Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.08371","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05aba426833f7a1e23a29cf1a1ce1ed4b4c60f364f4fb79e768dbdec05fff2d9","sha256:99738a8625895914a382042a34992605f2022c71bd02abc6b2cfe74719eddfdf"],"state_sha256":"29298cbc76d38cb18eaa0723f5cd2e183783a15ad9d4f64e081890e347457489"}